Josh Dillon, Last Revised January 2022
This notebook examines an individual antenna's performance over a whole season. This notebook parses information from each nightly rtp_summarynotebook (as saved to .csvs) and builds a table describing antenna performance. It also reproduces per-antenna plots from each auto_metrics notebook pertinent to the specific antenna.
import os
from IPython.display import display, HTML
display(HTML("<style>.container { width:100% !important; }</style>"))
# If you want to run this notebook locally, copy the output of the next cell into the next line of this cell.
# antenna = "004"
# csv_folder = '/lustre/aoc/projects/hera/H5C/H5C_Notebooks/_rtp_summary_'
# auto_metrics_folder = '/lustre/aoc/projects/hera/H5C/H5C_Notebooks/auto_metrics_inspect'
# os.environ["ANTENNA"] = antenna
# os.environ["CSV_FOLDER"] = csv_folder
# os.environ["AUTO_METRICS_FOLDER"] = auto_metrics_folder
# Use environment variables to figure out path to the csvs and auto_metrics
antenna = str(int(os.environ["ANTENNA"]))
csv_folder = os.environ["CSV_FOLDER"]
auto_metrics_folder = os.environ["AUTO_METRICS_FOLDER"]
print(f'antenna = "{antenna}"')
print(f'csv_folder = "{csv_folder}"')
print(f'auto_metrics_folder = "{auto_metrics_folder}"')
antenna = "156" csv_folder = "/home/obs/src/H6C_Notebooks/_rtp_summary_" auto_metrics_folder = "/home/obs/src/H6C_Notebooks/auto_metrics_inspect"
display(HTML(f'<h1 style=font-size:50px><u>Antenna {antenna} Report</u><p></p></h1>'))
import numpy as np
import pandas as pd
pd.set_option('display.max_rows', 1000)
import glob
import re
from hera_notebook_templates.utils import status_colors, Antenna
# load csvs and auto_metrics htmls in reverse chronological order
csvs = sorted(glob.glob(os.path.join(csv_folder, 'rtp_summary_table*.csv')))[::-1]
print(f'Found {len(csvs)} csvs in {csv_folder}')
auto_metric_htmls = sorted(glob.glob(auto_metrics_folder + '/auto_metrics_inspect_*.html'))[::-1]
print(f'Found {len(auto_metric_htmls)} auto_metrics notebooks in {auto_metrics_folder}')
Found 14 csvs in /home/obs/src/H6C_Notebooks/_rtp_summary_ Found 14 auto_metrics notebooks in /home/obs/src/H6C_Notebooks/auto_metrics_inspect
# Per-season options
mean_round_modz_cut = 4
dead_cut = 0.4
crossed_cut = 0.0
def jd_to_summary_url(jd):
return f'https://htmlpreview.github.io/?https://github.com/HERA-Team/H6C_Notebooks/blob/main/_rtp_summary_/rtp_summary_{jd}.html'
def jd_to_auto_metrics_url(jd):
return f'https://htmlpreview.github.io/?https://github.com/HERA-Team/H6C_Notebooks/blob/main/auto_metrics_inspect/auto_metrics_inspect_{jd}.html'
this_antenna = None
jds = []
# parse information about antennas and nodes
for csv in csvs:
df = pd.read_csv(csv)
for n in range(len(df)):
# Add this day to the antenna
row = df.loc[n]
if isinstance(row['Ant'], str) and '<a href' in row['Ant']:
antnum = int(row['Ant'].split('</a>')[0].split('>')[-1]) # it's a link, extract antnum
else:
antnum = int(row['Ant'])
if antnum != int(antenna):
continue
if np.issubdtype(type(row['Node']), np.integer):
row['Node'] = str(row['Node'])
if type(row['Node']) == str and row['Node'].isnumeric():
row['Node'] = 'N' + ('0' if len(row['Node']) == 1 else '') + row['Node']
if this_antenna is None:
this_antenna = Antenna(row['Ant'], row['Node'])
jd = [int(s) for s in re.split('_|\.', csv) if s.isdigit()][-1]
jds.append(jd)
this_antenna.add_day(jd, row)
break
# build dataframe
to_show = {'JDs': [f'<a href="{jd_to_summary_url(jd)}" target="_blank">{jd}</a>' for jd in jds]}
to_show['A Priori Status'] = [this_antenna.statuses[jd] for jd in jds]
df = pd.DataFrame(to_show)
# create bar chart columns for flagging percentages:
bar_cols = {}
bar_cols['Auto Metrics Flags'] = [this_antenna.auto_flags[jd] for jd in jds]
bar_cols[f'Dead Fraction in Ant Metrics (Jee)'] = [this_antenna.dead_flags_Jee[jd] for jd in jds]
bar_cols[f'Dead Fraction in Ant Metrics (Jnn)'] = [this_antenna.dead_flags_Jnn[jd] for jd in jds]
bar_cols['Crossed Fraction in Ant Metrics'] = [this_antenna.crossed_flags[jd] for jd in jds]
bar_cols['Flag Fraction Before Redcal'] = [this_antenna.flags_before_redcal[jd] for jd in jds]
bar_cols['Flagged By Redcal chi^2 Fraction'] = [this_antenna.redcal_flags[jd] for jd in jds]
for col in bar_cols:
df[col] = bar_cols[col]
z_score_cols = {}
z_score_cols['ee Shape Modified Z-Score'] = [this_antenna.ee_shape_zs[jd] for jd in jds]
z_score_cols['nn Shape Modified Z-Score'] = [this_antenna.nn_shape_zs[jd] for jd in jds]
z_score_cols['ee Power Modified Z-Score'] = [this_antenna.ee_power_zs[jd] for jd in jds]
z_score_cols['nn Power Modified Z-Score'] = [this_antenna.nn_power_zs[jd] for jd in jds]
z_score_cols['ee Temporal Variability Modified Z-Score'] = [this_antenna.ee_temp_var_zs[jd] for jd in jds]
z_score_cols['nn Temporal Variability Modified Z-Score'] = [this_antenna.nn_temp_var_zs[jd] for jd in jds]
z_score_cols['ee Temporal Discontinuties Modified Z-Score'] = [this_antenna.ee_temp_discon_zs[jd] for jd in jds]
z_score_cols['nn Temporal Discontinuties Modified Z-Score'] = [this_antenna.nn_temp_discon_zs[jd] for jd in jds]
for col in z_score_cols:
df[col] = z_score_cols[col]
ant_metrics_cols = {}
ant_metrics_cols['Average Dead Ant Metric (Jee)'] = [this_antenna.Jee_dead_metrics[jd] for jd in jds]
ant_metrics_cols['Average Dead Ant Metric (Jnn)'] = [this_antenna.Jnn_dead_metrics[jd] for jd in jds]
ant_metrics_cols['Average Crossed Ant Metric'] = [this_antenna.crossed_metrics[jd] for jd in jds]
for col in ant_metrics_cols:
df[col] = ant_metrics_cols[col]
redcal_cols = {}
redcal_cols['Median chi^2 Per Antenna (Jee)'] = [this_antenna.Jee_chisqs[jd] for jd in jds]
redcal_cols['Median chi^2 Per Antenna (Jnn)'] = [this_antenna.Jnn_chisqs[jd] for jd in jds]
for col in redcal_cols:
df[col] = redcal_cols[col]
# style dataframe
table = df.style.hide_index()\
.applymap(lambda val: f'background-color: {status_colors[val]}' if val in status_colors else '', subset=['A Priori Status']) \
.background_gradient(cmap='viridis', vmax=mean_round_modz_cut * 3, vmin=0, axis=None, subset=list(z_score_cols.keys())) \
.background_gradient(cmap='bwr_r', vmin=dead_cut-.25, vmax=dead_cut+.25, axis=0, subset=list([col for col in ant_metrics_cols if 'dead' in col.lower()])) \
.background_gradient(cmap='bwr_r', vmin=crossed_cut-.25, vmax=crossed_cut+.25, axis=0, subset=list([col for col in ant_metrics_cols if 'crossed' in col.lower()])) \
.background_gradient(cmap='plasma', vmax=4, vmin=1, axis=None, subset=list(redcal_cols.keys())) \
.applymap(lambda val: 'font-weight: bold' if val < dead_cut else '', subset=list([col for col in ant_metrics_cols if 'dead' in col.lower()])) \
.applymap(lambda val: 'font-weight: bold' if val < crossed_cut else '', subset=list([col for col in ant_metrics_cols if 'crossed' in col.lower()])) \
.applymap(lambda val: 'font-weight: bold' if val > mean_round_modz_cut else '', subset=list(z_score_cols.keys())) \
.applymap(lambda val: 'color: red' if val > mean_round_modz_cut else '', subset=list(z_score_cols.keys())) \
.bar(subset=list(bar_cols.keys()), vmin=0, vmax=1) \
.format({col: '{:,.4f}'.format for col in z_score_cols}) \
.format({col: '{:,.4f}'.format for col in ant_metrics_cols}) \
.format('{:,.2%}', na_rep='-', subset=list(bar_cols.keys())) \
.set_table_styles([dict(selector="th",props=[('max-width', f'70pt')])])
This table reproduces each night's row for this antenna from the RTP Summary notebooks. For more info on the columns, see those notebooks, linked in the JD column.
display(HTML(f'<h2>Antenna {antenna}, Node {this_antenna.node}:</h2>'))
HTML(table.render(render_links=True, escape=False))
| JDs | A Priori Status | Auto Metrics Flags | Dead Fraction in Ant Metrics (Jee) | Dead Fraction in Ant Metrics (Jnn) | Crossed Fraction in Ant Metrics | Flag Fraction Before Redcal | Flagged By Redcal chi^2 Fraction | ee Shape Modified Z-Score | nn Shape Modified Z-Score | ee Power Modified Z-Score | nn Power Modified Z-Score | ee Temporal Variability Modified Z-Score | nn Temporal Variability Modified Z-Score | ee Temporal Discontinuties Modified Z-Score | nn Temporal Discontinuties Modified Z-Score | Average Dead Ant Metric (Jee) | Average Dead Ant Metric (Jnn) | Average Crossed Ant Metric | Median chi^2 Per Antenna (Jee) | Median chi^2 Per Antenna (Jnn) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2459989 | RF_maintenance | 100.00% | 0.00% | 100.00% | 0.00% | - | - | 4.016073 | 12.900260 | 7.345939 | 9.342427 | 4.229192 | 9.308623 | 2.473989 | 1.185193 | 0.4003 | 0.0374 | 0.3063 | nan | nan |
| 2459988 | RF_maintenance | 100.00% | 0.00% | 100.00% | 0.00% | - | - | 5.039081 | 15.098841 | 8.533960 | 10.498185 | 5.910855 | 13.250126 | 2.203685 | 0.863744 | 0.4212 | 0.0366 | 0.3117 | nan | nan |
| 2459987 | RF_maintenance | 100.00% | 0.00% | 100.00% | 0.00% | - | - | 2.219743 | 12.631734 | 7.504429 | 10.368511 | 3.478798 | 8.014167 | 1.527689 | 2.388913 | 0.4622 | 0.0398 | 0.3598 | nan | nan |
| 2459986 | RF_maintenance | 100.00% | 0.00% | 100.00% | 0.00% | - | - | 3.481062 | 15.535400 | 8.366438 | 11.186942 | 4.246772 | 11.317789 | 1.346033 | 9.899216 | 0.4792 | 0.0382 | 0.3499 | nan | nan |
| 2459985 | RF_maintenance | 100.00% | 0.00% | 100.00% | 0.00% | - | - | 3.149243 | 13.991533 | 7.823937 | 10.425452 | 2.397417 | 8.659236 | 1.677296 | 2.463065 | 0.4496 | 0.0386 | 0.3514 | nan | nan |
| 2459984 | RF_maintenance | 100.00% | 0.00% | 100.00% | 0.00% | - | - | 2.407261 | 13.493964 | 7.901097 | 10.805990 | 2.625487 | 12.109887 | 1.093452 | 3.170391 | 0.4811 | 0.0411 | 0.3702 | nan | nan |
| 2459983 | RF_maintenance | 100.00% | 90.17% | 100.00% | 0.00% | - | - | 10.045402 | 13.154877 | 9.876355 | 10.214315 | 9.266661 | 11.189577 | 3.425093 | 6.814421 | 0.1074 | 0.0394 | 0.0516 | nan | nan |
| 2459982 | RF_maintenance | 100.00% | 0.00% | 100.00% | 0.00% | - | - | 2.233733 | 10.210803 | 6.762207 | 8.715913 | 1.820801 | 5.249557 | 0.451258 | 3.315519 | 0.5324 | 0.0385 | 0.3745 | nan | nan |
| 2459981 | RF_maintenance | 100.00% | 0.00% | 100.00% | 0.00% | - | - | 3.767135 | 12.121974 | 8.628629 | 10.860085 | 6.409224 | 12.381350 | 0.640346 | 1.271861 | 0.4210 | 0.0404 | 0.3254 | nan | nan |
| 2459980 | RF_maintenance | 100.00% | 0.00% | 100.00% | 0.00% | - | - | 3.364154 | 11.697209 | 7.762570 | 9.929517 | 6.092929 | 10.820870 | 2.720316 | 5.372100 | 0.4757 | 0.0398 | 0.3435 | nan | nan |
| 2459979 | RF_maintenance | 100.00% | 0.00% | 100.00% | 0.00% | - | - | 3.830079 | 12.191898 | 7.130735 | 9.285540 | 4.903373 | 10.160338 | 1.729278 | 1.999588 | 0.4126 | 0.0382 | 0.3200 | nan | nan |
| 2459978 | RF_maintenance | 100.00% | 0.00% | 100.00% | 0.00% | - | - | 3.709871 | 12.403590 | 7.726980 | 9.996973 | 4.768964 | 10.994431 | 0.784584 | 1.195361 | 0.4134 | 0.0362 | 0.3277 | nan | nan |
| 2459977 | RF_maintenance | 100.00% | 0.00% | 100.00% | 0.00% | - | - | 3.767804 | 13.168940 | 7.550951 | 9.861564 | 4.534933 | 11.315394 | 0.323269 | 1.374423 | 0.3845 | 0.0418 | 0.2943 | nan | nan |
| 2459976 | RF_maintenance | 100.00% | 0.00% | 100.00% | 0.00% | - | - | 3.869857 | 12.648395 | 7.986260 | 10.266366 | 4.752534 | 10.880413 | 1.092430 | 1.484064 | 0.4190 | 0.0375 | 0.3273 | nan | nan |
auto_metrics notebooks.¶htmls_to_display = []
for am_html in auto_metric_htmls:
html_to_display = ''
# read html into a list of lines
with open(am_html) as f:
lines = f.readlines()
# find section with this antenna's metric plots and add to html_to_display
jd = [int(s) for s in re.split('_|\.', am_html) if s.isdigit()][-1]
try:
section_start_line = lines.index(f'<h2>Antenna {antenna}: {jd}</h2>\n')
except ValueError:
continue
html_to_display += lines[section_start_line].replace(str(jd), f'<a href="{jd_to_auto_metrics_url(jd)}" target="_blank">{jd}</a>')
for line in lines[section_start_line + 1:]:
html_to_display += line
if '<hr' in line:
htmls_to_display.append(html_to_display)
break
These figures are reproduced from auto_metrics notebooks. For more info on the specific plots and metrics, see those notebooks (linked at the JD). The most recent 100 days (at most) are shown.
for i, html_to_display in enumerate(htmls_to_display):
if i == 100:
break
display(HTML(html_to_display))
| Ant | Node | A Priori Status | Worst Metric | Worst Modified Z-Score | nn Shape Modified Z-Score | ee Shape Modified Z-Score | nn Power Modified Z-Score | ee Power Modified Z-Score | nn Temporal Variability Modified Z-Score | ee Temporal Variability Modified Z-Score | nn Temporal Discontinuties Modified Z-Score | ee Temporal Discontinuties Modified Z-Score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 156 | N12 | RF_maintenance | nn Shape | 12.900260 | 12.900260 | 4.016073 | 9.342427 | 7.345939 | 9.308623 | 4.229192 | 1.185193 | 2.473989 |
| Ant | Node | A Priori Status | Worst Metric | Worst Modified Z-Score | nn Shape Modified Z-Score | ee Shape Modified Z-Score | nn Power Modified Z-Score | ee Power Modified Z-Score | nn Temporal Variability Modified Z-Score | ee Temporal Variability Modified Z-Score | nn Temporal Discontinuties Modified Z-Score | ee Temporal Discontinuties Modified Z-Score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 156 | N12 | RF_maintenance | nn Shape | 15.098841 | 15.098841 | 5.039081 | 10.498185 | 8.533960 | 13.250126 | 5.910855 | 0.863744 | 2.203685 |
| Ant | Node | A Priori Status | Worst Metric | Worst Modified Z-Score | ee Shape Modified Z-Score | nn Shape Modified Z-Score | ee Power Modified Z-Score | nn Power Modified Z-Score | ee Temporal Variability Modified Z-Score | nn Temporal Variability Modified Z-Score | ee Temporal Discontinuties Modified Z-Score | nn Temporal Discontinuties Modified Z-Score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 156 | N12 | RF_maintenance | nn Shape | 12.631734 | 2.219743 | 12.631734 | 7.504429 | 10.368511 | 3.478798 | 8.014167 | 1.527689 | 2.388913 |
| Ant | Node | A Priori Status | Worst Metric | Worst Modified Z-Score | nn Shape Modified Z-Score | ee Shape Modified Z-Score | nn Power Modified Z-Score | ee Power Modified Z-Score | nn Temporal Variability Modified Z-Score | ee Temporal Variability Modified Z-Score | nn Temporal Discontinuties Modified Z-Score | ee Temporal Discontinuties Modified Z-Score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 156 | N12 | RF_maintenance | nn Shape | 15.535400 | 15.535400 | 3.481062 | 11.186942 | 8.366438 | 11.317789 | 4.246772 | 9.899216 | 1.346033 |
| Ant | Node | A Priori Status | Worst Metric | Worst Modified Z-Score | nn Shape Modified Z-Score | ee Shape Modified Z-Score | nn Power Modified Z-Score | ee Power Modified Z-Score | nn Temporal Variability Modified Z-Score | ee Temporal Variability Modified Z-Score | nn Temporal Discontinuties Modified Z-Score | ee Temporal Discontinuties Modified Z-Score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 156 | N12 | RF_maintenance | nn Shape | 13.991533 | 13.991533 | 3.149243 | 10.425452 | 7.823937 | 8.659236 | 2.397417 | 2.463065 | 1.677296 |
| Ant | Node | A Priori Status | Worst Metric | Worst Modified Z-Score | ee Shape Modified Z-Score | nn Shape Modified Z-Score | ee Power Modified Z-Score | nn Power Modified Z-Score | ee Temporal Variability Modified Z-Score | nn Temporal Variability Modified Z-Score | ee Temporal Discontinuties Modified Z-Score | nn Temporal Discontinuties Modified Z-Score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 156 | N12 | RF_maintenance | nn Shape | 13.493964 | 2.407261 | 13.493964 | 7.901097 | 10.805990 | 2.625487 | 12.109887 | 1.093452 | 3.170391 |
| Ant | Node | A Priori Status | Worst Metric | Worst Modified Z-Score | ee Shape Modified Z-Score | nn Shape Modified Z-Score | ee Power Modified Z-Score | nn Power Modified Z-Score | ee Temporal Variability Modified Z-Score | nn Temporal Variability Modified Z-Score | ee Temporal Discontinuties Modified Z-Score | nn Temporal Discontinuties Modified Z-Score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 156 | N12 | RF_maintenance | nn Shape | 13.154877 | 10.045402 | 13.154877 | 9.876355 | 10.214315 | 9.266661 | 11.189577 | 3.425093 | 6.814421 |
| Ant | Node | A Priori Status | Worst Metric | Worst Modified Z-Score | ee Shape Modified Z-Score | nn Shape Modified Z-Score | ee Power Modified Z-Score | nn Power Modified Z-Score | ee Temporal Variability Modified Z-Score | nn Temporal Variability Modified Z-Score | ee Temporal Discontinuties Modified Z-Score | nn Temporal Discontinuties Modified Z-Score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 156 | N12 | RF_maintenance | nn Shape | 10.210803 | 2.233733 | 10.210803 | 6.762207 | 8.715913 | 1.820801 | 5.249557 | 0.451258 | 3.315519 |
| Ant | Node | A Priori Status | Worst Metric | Worst Modified Z-Score | nn Shape Modified Z-Score | ee Shape Modified Z-Score | nn Power Modified Z-Score | ee Power Modified Z-Score | nn Temporal Variability Modified Z-Score | ee Temporal Variability Modified Z-Score | nn Temporal Discontinuties Modified Z-Score | ee Temporal Discontinuties Modified Z-Score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 156 | N12 | RF_maintenance | nn Temporal Variability | 12.381350 | 12.121974 | 3.767135 | 10.860085 | 8.628629 | 12.381350 | 6.409224 | 1.271861 | 0.640346 |
| Ant | Node | A Priori Status | Worst Metric | Worst Modified Z-Score | nn Shape Modified Z-Score | ee Shape Modified Z-Score | nn Power Modified Z-Score | ee Power Modified Z-Score | nn Temporal Variability Modified Z-Score | ee Temporal Variability Modified Z-Score | nn Temporal Discontinuties Modified Z-Score | ee Temporal Discontinuties Modified Z-Score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 156 | N12 | RF_maintenance | nn Shape | 11.697209 | 11.697209 | 3.364154 | 9.929517 | 7.762570 | 10.820870 | 6.092929 | 5.372100 | 2.720316 |
| Ant | Node | A Priori Status | Worst Metric | Worst Modified Z-Score | ee Shape Modified Z-Score | nn Shape Modified Z-Score | ee Power Modified Z-Score | nn Power Modified Z-Score | ee Temporal Variability Modified Z-Score | nn Temporal Variability Modified Z-Score | ee Temporal Discontinuties Modified Z-Score | nn Temporal Discontinuties Modified Z-Score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 156 | N12 | RF_maintenance | nn Shape | 12.191898 | 3.830079 | 12.191898 | 7.130735 | 9.285540 | 4.903373 | 10.160338 | 1.729278 | 1.999588 |
| Ant | Node | A Priori Status | Worst Metric | Worst Modified Z-Score | nn Shape Modified Z-Score | ee Shape Modified Z-Score | nn Power Modified Z-Score | ee Power Modified Z-Score | nn Temporal Variability Modified Z-Score | ee Temporal Variability Modified Z-Score | nn Temporal Discontinuties Modified Z-Score | ee Temporal Discontinuties Modified Z-Score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 156 | N12 | RF_maintenance | nn Shape | 12.403590 | 12.403590 | 3.709871 | 9.996973 | 7.726980 | 10.994431 | 4.768964 | 1.195361 | 0.784584 |
| Ant | Node | A Priori Status | Worst Metric | Worst Modified Z-Score | ee Shape Modified Z-Score | nn Shape Modified Z-Score | ee Power Modified Z-Score | nn Power Modified Z-Score | ee Temporal Variability Modified Z-Score | nn Temporal Variability Modified Z-Score | ee Temporal Discontinuties Modified Z-Score | nn Temporal Discontinuties Modified Z-Score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 156 | N12 | RF_maintenance | nn Shape | 13.168940 | 3.767804 | 13.168940 | 7.550951 | 9.861564 | 4.534933 | 11.315394 | 0.323269 | 1.374423 |
| Ant | Node | A Priori Status | Worst Metric | Worst Modified Z-Score | nn Shape Modified Z-Score | ee Shape Modified Z-Score | nn Power Modified Z-Score | ee Power Modified Z-Score | nn Temporal Variability Modified Z-Score | ee Temporal Variability Modified Z-Score | nn Temporal Discontinuties Modified Z-Score | ee Temporal Discontinuties Modified Z-Score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 156 | N12 | RF_maintenance | nn Shape | 12.648395 | 12.648395 | 3.869857 | 10.266366 | 7.986260 | 10.880413 | 4.752534 | 1.484064 | 1.092430 |